After the validation scores arrive, the team nudges layer count and pass count, retrains, and scores again. They keep calling that loop “the test.” Where should a tester place that loop?
Select an answer to reveal the explanation.
Short Explanation
Nudging layer count and pass count, retraining, and scoring again is tune-the-model. That loop stays inside model generation and off the independent test dataset. Calling it the test, or moving it to Chapter 6 drift, misses that placement.
Full Explanation
Tuning is hyperparameter adjustment plus retrain, distinct from the later test step. Calling the loop “the test,” turning it into an engineering search, or moving it to Chapter 6 drift misses that placement.